Fig. 2.

1 – Four Basic Image Types & Corresponding Histograms

 Fig. 2.5 – (a) Four Basic Image Types
(b) Corresponding Histogram Equalized Images
(c) Histograms of the Images in (b)
Fig. 2.7 – (a) Image of Mars Moon Phobos Taken By Global Surveyor
(b) Histogram of the Image in (a)

Fig. 2.8 – (a) Transformation Function for Histogram Equalization

(b) Histogram Equalized Image
 (c) Histogram of (b)

Fig. 2.9 – (a) Specified Histogram

(b) Transformations
(c) Enhanced Image Using Mappings from Curve (2)
(d) Histogram of (c)
 Fig. 2.10 – (a) Original Image
(b) Result of Global Histogram Equalization
 (c) Result of Local Histogram Equalization applied to (a) using a
Neighborhood of size 3 X 3

Fig. 2.13 – (a) Original Image of size 500X500 Pixels

(b) – (f) Results of Smoothing with Square Averaging Filter Masks of Sizes
m = 3, 5, 9, 15 and 35 Respectively
The Black Squares at the Top are of Sizes 3, 9, 15, 25, 35, 45 and 55 Pixels,
Their Borders are 25 Pixels Apart
The Letters at the Bottom Range in Size from 10 to 24 Points in increments of
2 Points
The Large Letter at the Top is 60 Points
The Vertical Bars are 5 Pixels Wide and 100 Pixels High
Their Separation is 20 Pixels
The Diameter of the Circle is 25 Pixels and their Borders are 15 Pixels Apart
Their Intensity Levels Range from 0% to 100% Black in increments of 20%
The Background of the Image is 10% black
The Noisy Rectangles are of Size 50X120 Pixels

Fig. 2.14 – (a) Image of Size 528X485 Pixels from the Hubble Space
Telescope
(b) Image Filtered with a 15X15 Averaging Mask
(c) Result of Thresholding (b)
Fig. 2.15 – (a) X-Ray Image of Circuit Board Corrupted by Salt and Pepper
Noise
(b) Noise Reduction with a 3X3 Averaging Mask
(c) Noise Reduction with a 3X3 Median Filter
Fig. 2.16 – Illustration of the First and Second Derivatives of a 1-D Digital
Function Representing a Section of a Horizontal Intensity Profile from an
Image
Fig. 2.17 – (a) Blurred Image of the North Pole of the Moon
(b) Laplacian without Scaling
 (c) Laplacian with Scaling
(d) Image Sharpened using the Mask I
(e) Result of using the Mask II

Fig. 2.18 – 1-D Illustration of the Mechanics of Unsharp Masking

(a) Original Signal
(b) Blurred Signal with Original Shown Dashed for Reference
(c) Unsharp Mask
(d) Sharpened Signal obtained by adding (c) to (a)

Fig. 2.19 – (a) Original Image

(b) Result of Blurring with a Gaussian Filter
(c) Unsharp Mask
(d) Result of using Unsharp Masking
(e) Result of using High Boost Filtering
Fig. 2.20 – (a) Optical Image of Contact Lens
(b) Sobel Gradient
Fig. 2.21 – (a) SEM Image of a Damaged Integrated Circuit
(b) Fourier Spectrum of (a)
Fig. 2.22 – Result of Filtering the Image in Fig. 2.21(a) by setting 0 the term
F(M/2, N/2) in the Fourier Transform
 Fig. 2.23 – Top Row: Frequency Domain Filters
Bottom Row: Corresponding Filtered Images obtained using Eq. 6,
a = 0.85 is used in (c) to obtain (f)

Fig. 2.24 – (a) A Simple Image

(b) Result of Blurring with a Gaussian LPF without Padding
(c) Result of LPF with Padding

Fig. 2.25 – 2-D Image Periodicity Inherent in using the DFT

 (a) Periodicity Without Image Padding
(b) Periodicity after Padding With 0s (Black)
The Dashed areas in the center correspond to the Image in Fig. 2.24(a)

Fig. 2.26 – (a) Original Filter Specified in the Frequency Domain

(b) Spatial Representation Obtained by Computing the IDFT of (a)
(c) Result of Padding (b) to twice its Length
(d) Corresponding Filter in the Frequency Domain Obtained by Computing the
DFT of (c)
Fig. 2.27 – (a) Image Resulting from Multiplying by 0.5 the Phase Angle and
then Computing the IDFT
(b) The Result of Multiplying the Phase by 0.25.
The Spectrum was not changed in either of the two cases
 Fig. 2.28 – (a) An M X N image, f
(b) Padded Image, fp of Size P X Q
(c) Result of Multiplying fp by (-1)x+y
(d) Spectrum of Fp
(e) Centered Gaussian Low Pass Filter, H of Size P X Q
(f) Spectrum of the Product HFp
(g) gp, the Product of (-1)x+y and the Real Part of IDFT of HFp
(h) Final Result, g, Obtained by cropping the First M Rows and N
Columns of gp
 Fig. 2.29 – (a) Image of a Building
(b) Its Spectrum

Fig. 2.30 – (a) A Spatial Mask and Perspective Plot of its Corresponding
Frequency Domain Filter
(b) Filter Shown as an Image
(c) Result of Filtering Fig. 2.29(a) in the Frequency Domain with the
Filter in (b)
(d) Result of Filtering the Same Image with the Spatial Filter in (a)
Fig. 2.31 – (a) Perspective Plot of an Ideal Low Pass Filter Transfer Function
(b) Filter Displayed as an Image
(c) Filter Radial Cross Section
 Fig. 2.32 – (a) Test Pattern of size 688 X 688 Pixels
(b) Its Fourier Spectrum
The Spectrum is Double the Image Size Due to Padding but is Shown
Half Size So That It Fits in the Page. The Superimposed Circles have
Radii Equal to 10, 30, 60, 160 and 460 with respect to the Full Size
Spectrum Image. These Radii enclose 87.0, 93.1, 95.7, 97.8 and 99.2%
of the Padded Image Power Respectively
 Fig. 2.33 – (a) Original Image
(b) – (f) Results of Filtering using ILPFs with Cutoff Frequencies Set to
Radii Values 10, 30, 60, 160 and 460 as shown in 2.32(b)
The Power Removed by these Filters was 13, 6.9, 4.3, 2.2 and 0.8% of
the Total Respectively

Fig. 2.34 – (a) Representation in the Spatial Domain of an ILPF of

Radius 5 and Size 1000 X 1000
(b) Intensity Profile of a Horizontal Line Passing Trough the Center of the
Image
Fig. 2.35 – (a) Perspective Plot of a Butterworth Low Pass Filter Transfer
Function
(b) Filter Displayed as an Image
(c) Filter Radial Cross Sections of Orders 1 through 4
 Fig. 2.36 – (a) Original Image
(b) – (f) – Results of Filtering using BLPFs of Order 2 with Cutoff
Frequencies at the Radii Shown in Fig. 2.32
Compare with Fig. 2.33

Fig. 2.37 – (a) – (d) Spatial Representation of BLPFs of Order 1, 2, 5 and 20

& Corresponding Intensity Profiles Through the Center of the Filters
 Fig. 2.38 – (a) Perspective Plot of GLPF Transfer Function
(b) Filter Displayed as an Image
(c) Filter Radial Cross Sections for Various Values of D0

Fig. 2.39 – (a) Original Image

(b) – (f) – Results of Filtering using GLPFs with Cutoff Frequencies at the
Radii Shown in Fig. 2.32
Compare with Fig. 2.33 and Fig. 2.36
Fig. 2.40 – (a) Sample Text of Low Resolution
(b) Result of Filtering with a GLPF
 Fig. 2.41 – (a) Original Image (784 X 732 Pixels)
(b) Result of Filtering using a GLPF with D0 = 100
(c) Result of Filtering using a GLPF with D0 = 80
Note the Reduction in Fine Skin Lines in the Magnified Sections of (b) and (c)
Fig. 2.42 – (a) Image Showing Prominent Horizontal Scan Lines
(b) Result of Filtering using a GLFP with D0 = 50
(c) Result of Filtering using a GLPF with D0 = 20
Fig. 2.43 – Top Row: Perspective Plot, Image Representation and Cross
Section of a Typical Ideal High Pass Filter
Middle & Bottom Rows: The Same Sequence for BHPFs and GHPFs
 Fig. 2.44 – Spatial Representation of Typical (a) Ideal (b) Butterworth
(c) Gaussian Frequency Domain HPFs and Corresponding Intensity Profiles
through their Centers

Fig. 2.45 – Results of High Pass Filtering the Images in Fig. 2.32(a) using an
IHPF with D0 = 30, 60 and 160
Fig. 2.46 – Results of High Pass Filtering the Image in Fig. 2.32(a) using a
BHPF of Order 2 with D0 = 30, 60 and 160, Corresponding to the Circles in
Fig. 2.32(b)
These Results are Much Smoother than Those Obtained with an IHPF

Fig. 2.47 – Results of High Pass Filtering the Image in Fig. 2.32(a) using a
GHPF with D0 = 30, 60 and 160 & Corresponding to the Circles in Fig.
2.32(b)
Compare with Fig. 2.45 and Fig. 2.46
 Fig. 2.48 – (a) Thumb Print
(b) Result of High Pass Filtering (a)
(c) Result of Thresholding (b)
 Fig. 2.49 – (a) Band Reject Gaussian Filter
(b) Corresponding Band Pass Filter
The Thin Black Border in (a) was added for Clarity, It is Not Part of the Data
 Fig. 2.50 – (a) Sampled News Paper Image Showing a Moiré Pattern
(b) Spectrum
(c) Butterworth Notch Reject Filter Multiplied by the Fourier Transform
(d) Filtered Image
Fig. 2.51 – (a) 674 X 674 Image of Saturn Rings Showing Nearly Periodic
Interference
(b) Spectrum: The Burst of Energy in the Vertical Axis near the Origin
Correspond to the Interference Pattern
(c) A Vertical Notch Reject Filter
(d) Result of Filtering
The Thin Border in (c) wad added for Clarity. It is not Part of the Data
 Fig. 2.52 – (a) Image Containing a Region of Constant Intensity
(b) Image Showing the Boundary of the Inner Region Obtained from Intensity
Discontinuities
(c) Result of Segmenting the Image into Two Regions
(d) Image Containing a Textured Region
(e) Result of Edge Computations
(f) Result of Segmentation Based on Region Properties
 Fig. 2.53 – (a) An Image
(b) Horizontal Intensity Profile through the Center of the Image Including the
Isolated Noise Point
(c) Simplified Profile
 Fig. 2.54 – (a) Point Detection Mask
(b) X-Ray Image of Turbine Blade with a Porosity, The Porosity Contains
a Single Black Pixel
(c) Result of Convolving the Mask with the Image
(d) Result of Using Eq. Showing a Single Point
 Fig. 2.55 – (a) Original Image
(b) Laplacian Image, The Magnified Section Shows the Positive or
Negative Double Line Effect Characteristic of the Laplacian
(c) Absolute Value of the Laplacian
(d) Positive Value of the Laplacian
 Fig. 2.56 – (a) Image of a Wire Bond Template
(b) Result of Processing With the +450 Line Detector Mask
(c) Zoomed View of the Top Left Region of (b)
(d) Zoomed View of the Bottom Right Region of (b)
(e) The Image in (b) with all Negative Values Set to Zero
(f) All Points Whose Values Satisfied the Condition g ≥ T, Where g is the
Image in (e)
 Fig. 2.57 – (a) Ideal Representation of Step
(b) Ideal Representation of Ramp
(c) Ideal Representation of Roof Edge and Their Corresponding Intensity
Profiles
Fig. 2.58 – A 1508 X 1970 Image Showing (Zoomed) Actual Ramp (Bottom,
Left), Step (Top, Right) and Roof Edge Profiles
The Profiles are from Dark to Light in the Areas Indicated by the Short Line
Segments Shown in the Small Circles
The Ramp and Step Profiles Span 9 Pixels and 2 Pixels Respectively
The Base of the Roof Edge is 3 Pixels

Fig. 2.59 – (a) Two Regions of Constant Intensity Separated by an Ideal

Vertical Ramp Edge
(b) Detail Near the Edge, Showing a Horizontal Intensity Profile, Together
with Its First and Second Derivatives
 Fig. 2.60 – First Column: Image and Intensity Profiles of a Ramp Edge
Corrupted by Random Gaussian Noise of Zero Mean and Standard Deviations
of 0.0, 0.1, 1.0, 10.0 intensity Levels Respectively
Second Column: First Derivatives and Intensity Profiles
Third Column: Second Derivatives and Intensity Profiles
Fig. 2.61 – Using the Gradient to Determine Edge Strength and Direction at a
Point
Note that the Edge is Perpendicular to the Direction of the Gradient Vector at
that Point where the Gradient is computed. Each Square in the Figure
represents one Pixel
Fig. 2.64 – (a) Original Image of Size 834 X 1114 Pixels with Intensity Values
Scaled to the Range [0, 1]
(b) Mod of │gx│, The Component of the Gradient in the x – Direction,
obtained Using the Sobel Mask
(c) │gy│
(d) The gradient Image, Mod of │gx│ + │gy│
 Fig. 2.65 – Gradient Angle Image
Areas of Constant Intensity in this Image Indicate that the Direction of
the Gradient Vector is the same at all the Pixel Locations in those
Regions
 Fig. 2.66 – Same Sequence as in Fig. 2.62, but with the Original Image
Smoothed Using a 5 X 5 Averaging Filter Prior to Edge Detection

Fig. 2.67 – Diagonal Edge Detection

(a) Result of Using the Mask
(b) Result of Using the Mask
The Input Image in Both the Cases is

Fig. 2.68 – (a) Threshold Version of the Image in Fig. 2.62(d) with the
Threshold Selected as 33% of the Highest Value in the Image; This Threshold
is high enough to Eliminate Most of the Brick Edges in the Gradient Image
(b) Threshold Version of the Image in Fig. 2.64(d), Obtained Using a
Threshold Equal to 33% of the Highest Value in that Image
Fig. 2.69 – (a) Three Dimensional Plot of the Negative of the LoG
(b) Negative of the LoG Displayed as an Image
(c) Showing Zero Crossings
(d) 5 X 5 Mask Approximation to the Shape in (a)
Fig. 2.70 – (a) Original Image of Size 834 X 1114 Pixels, with Intensity
Values Scaled to the Range [0, 1]
(b) Results of Steps 1 and 2 of the Marr – Hildreth Algorithm
(c) Zero Crossings of (b) Using a Threshold of 0
(d) Zero Crossings Found Using a Threshold Equal To 4% Maximum
Value of the Image in (b)
Fig. 2.71 – (a) Negatives of the LoG (Solid) and DoG (Dotted) Profiles using a
Standard Deviation Ratio of 1.75:1
(b) Profiles Obtained Using a Ratio of 1.6:1
Fig 2.72 – (a) Two Possible Orientations of a Horizontal Edge in a 3 X 3
Neighborhood
(b) Ranges of Values of α, The Direction Angle of the Edge Normal, for a
Horizontal Edge
(c) The Angle Ranges of the Edge Normals for the Four Types of Edge
Directions in a 3 X 3 Neighborhood
Fig 2.73 – (a) Original Image of Size 834 X 1114 Pixels, with Intensity Values
Scaled to the Range [0, 1]
(c) Thresholded Gradient of the Smoothed Image
(d) Image Obtained Using the Marr-Hilderth Algorithm
(e) Image Obtained Using the Canny Algorithm
Fig 2.74 – (a) Original Head CT Image of Size 512 X 512 Pixels with
Intensity Values Scaled to the Range [0, 1]
(b) Thresholded Gradient of the Smoothed Image
(c) Image Obtained Using the Marr-Hilderth Algorithm
(d) Image Obtained Using the Canny Algorithm
Fig 2.75 – A 534 X 566 Image of the Rear of a Vehicle
(c) Gradient Magnitude Image
(d) Horizontally Connected Edge Pixels
(e) Vertically Connected Edge Pixels
(f) The Logical OR of the Two Preceding Images
(g) Final Result Obtained Using Morphological Thinning
Fig 2.76 – Illustration of the Iterative Polygonal Fit Algorithm
Fig 2.77 – (a) A Set of Points in a Clockwise Path (The Points Labeled A and
B were Chosen as the Starting Vertices
(b) The Distance from C to the Line Passing Through A and B is the Largest
of all the Points Between A and B & also Passed the Threshold Test, So C is a
New Vertex
(d) – (g) Various Stages of the Algorithm
(h) The Final Vertices, Shown Connected with Straight Lines to Form a
Polygon
 Fig 2.78 – (a) A 550 X 566 X-Ray Image of a Human Tooth
(b) Gradient Image
(c) Result of Majority Filtering
(d) Result of Morphological Shrinking
(e) Result of Morphological Cleaning
(f) Skeleton
(g) Spur Reduction
(h) – (j) Polynomial Fit Using Thresholds of Approximately 0.5%, 1% and 2%
of Image Width (T = 3, 6, 12)
(k) Boundary in (j) Smoothed with a 1-D Averaging Filter of Size 1 X 31
(l) Boundary in (h) Smoothed with the Same Filter
Fig 2.79 – (a) xy-Plane
(b) Parameter Space
 Fig 2.80 – (a) (ρ, θ) Parameterization of Line in the xy – Plane
(b) Sinusoidal Curves in the ρθ – Plane; The Point of Intersection (ρ’, θ’)
Corresponds to the Line Passing Through Points (xi, yi) and (xj, yj) in the xy –
Plane
(c) Division of the ρθ – Plane into the Accumulator Cells
Fig 2.81 – (a) Image of Size 101 X 101 Pixels Containing Five Points
(b) Corresponding Parameter Space
 Fig 2.82 – (a) A 502 X 564 Aerial Image of an Airport
(b) Edge Image Obtained Using Canny’s Algorithm
(c) Hough Parameter Space
(d) Lines in the Image Plane Corresponding to the Points Highlighted by the
Boxes
(e) Lines Superimposed on the Original Image
Fig 2.83 – Intensity Histogram that can be Partitioned
(a) By a Single Threshold
(b) By Dual Thresholds
 Fi 2.84 – (a) Noiseless 8-Bit Image
(b) Image with Additive Gaussian Noise of Mean 0 and Standard Deviation of
10 Intensity Levels
(c) Image with Additive Gaussian Noise of Mean 0 and Standard Deviation of
50 Intensity Levels
(d – (f) Corresponding Histograms
 Fig 2.85 – (a) Noisy Image
(b) Intensity Ramp in the Range [0.2 0.6]
(c) Product of (a) and (b)
(d) – (f) Corresponding Histograms
 Fig 2.86 – (a) Noisy Finger Print
(b) Histogram
(c) Segmented Result Using a Global Threshold
 Fig 2.87 – (a) Original Image
(b) Histogram
(c) Segmentation Result Using the Basic Global Algorithm
(d) Result Obtained Using Otsu’s Method
 Fig 2.88 – (a) Noisy Image
(b) Its Histogram
(c) Result Obtained Using Otsu’s Method
(d) Noisy Image Smoothed Using a 5 X 5 Averaging Mask
(e) Its Histogram
(f) Result of Thresholding Using Otsu’s Method
 Fig 2.89 – (a) Noisy Image
(b) Its Histogram
(c) Result Obtained Using Otsu’s Method
(d) Noisy Image Smoothed Using a 5 X 5 Averaging Mask
(e) Its Histogram
(f) Result of Thresholding Using Otsu’s Method
 Fig 2.90 – (a) Noisy Image
(b) Its Histogram
(c) Gradient Magnitude Image Thresholded at the 99.7 Percentile
(d) Image Formed as Product of (a) and(c)
(e) Histogram of the Non-Zero Pixels in the Image in (d)
(f) Result of Segmenting Image (a) With the Otsu Threshold Based on the
Histogram in (e)
The Threshold was 134, which is approximately Midway between the Peaks in
this Histogram
 Fig 2.91 – (a) Image of yeast Cells
(b) Its Histogram
(c) Segmentation of (a) with Otsu’s Method Using the Histogram in (b)
(d) Thresholded Absolute Laplacian
(e) Histogram of the Non-Zero Pixels in the Product of (a) and (d)
(f) Original Image Thresholded Using Otsu’s Method based on the Histogram
in (e)
 Fig 2.93 – (a) Noisy, Shaded Image
(b) Its Histogram
(c) Segmentation of (a) Using the Iterative Global Algorithm
(d) Result Obtained Using Otsu’s Method
(e) Image Subdivided into Six Sub-Images
(f) Results of Applying Otsu’s Method to each Sub-Image Individually
Fig 2.94 – Histograms of the Six Images in Fig 2.93 (e)
 Fig 2.95 – (a) Image of Yeast Cells
(b) Image Segmented Using the Dual Thresholding Approach
(c) Image of Local Standard Deviations
(d) Result obtained using Local Thresholding
 Fig 2.95 – (a) X-Ray Image of a Defective Weld
(b) Its Histogram
(c) Initial Seed Image
(d) Final Seed Image
(e) Absolute Value of the Difference between (a) and (c)
(f) Its Histogram
(g) Difference Image Thresholded Using Dual Thresholds
(h) Difference Image Thresholded With the Smallest of the Dual Thresholds
(i) Segmentation Result Obtained by Region Growing
 Fig 2.96 – (a) Partitioned Image
(b) Corresponding Quad Tree
R represents the Entire Image Region
 Fig 2.97 – (a) Image of the Cygnus Loop Supernova, Taken in the X-Ray
Band by NASA’s Hubble Telescope
(b) – (d) Results of Limiting the Smallest Allowed Quad Region to Sizes of 32
X 32, 16 X 16 and 8 X 8 Pixels Respectively